AIbase
EN
Explore
Voice MCP
V

Voice MCP

An MCP server that supports voice interaction with LLMs such as Claude. You only need an OpenAI API key and a microphone/speaker to have a real-time voice conversation.
Voice processingArtificial intelligence chatbots#Voice Interaction#Real-time Conversation#Multi-platform#Low Latency.Python
2.5 points
3

What is Voice MCP?

Voice MCP is a Model Context Protocol (MCP) server that allows users to interact with Claude and other large language models via voice. You only need an OpenAI API key and a microphone/speaker to have a voice conversation.

How to Use Voice MCP?

You can add Voice MCP to the Claude desktop application through simple command-line operations. After configuration, you can directly talk to Claude via voice and get voice responses.

Use Cases

Suitable for scenarios that require voice interaction, such as daily Q&A, voice assistants, educational tutoring, etc. It is especially suitable for users who want to have natural conversations with AI via voice.

Main Features

Voice ConversationSupports real-time voice conversations with Claude, providing a natural and smooth communication experience.
Multiple Transmission MethodsSupports local microphone or LiveKit room communication to meet the needs of different scenarios.
Strong CompatibilitySupports any OpenAI-compatible STT/TTS service, including local or cloud services.
Low LatencyProvides a low-latency voice interaction experience to ensure real-time conversations.
MCP IntegrationSeamlessly integrates with the Claude desktop application and other MCP clients to enhance the user experience.

Advantages and Limitations

Advantages
Supports voice interaction to enhance the user experience
Strong compatibility, can use multiple STT/TTS services
Low latency to ensure real-time conversations
Easy to integrate into the Claude desktop application
Limitations
Requires microphone and speaker devices
Some functions depend on external services (such as LiveKit)
May require additional system permission configuration

How to Use

Get an OpenAI API Key
Register on the OpenAI official website and obtain an API key for voice recognition and speech synthesis services.
Install Voice MCP
Install the Voice MCP server via uvx, Docker, or pip.
Configure Claude Desktop
Add Voice MCP to the configuration file of the Claude desktop application.
Start and Test
After starting Voice MCP, try voice interaction through the Claude desktop application.

Usage Examples

Daily Q&AUsers ask questions to Claude via voice, such as inquiries about the weather, news, or knowledge questions.
Tell a JokeUsers request Claude to tell a joke and listen to the result via voice.
Voice Interactive LearningStudents conduct language learning or knowledge explanation with Claude via voice.

Frequently Asked Questions

What devices do I need to use Voice MCP?
What if my microphone doesn't work?
Does Voice MCP support Chinese?
How to debug Voice MCP?

Related Resources

GitHub Project Page
Source code and documentation for Voice MCP
LiveKit Official Documentation
Usage guide and configuration instructions for the LiveKit server
Claude Desktop Application Documentation
Usage guide and configuration method for the Claude desktop application
Installation
Copy the following command to your Client for configuration
{
  "mcpServers": {
    "voice-mcp": {
      "command": "uvx",
      "args": ["voice-mcp"],
      "env": {
        "OPENAI_API_KEY": "your-openai-key"
      }
    }
  }
}

{
  "mcpServers": {
    "voice-mcp": {
      "command": "docker",
      "args": [
        "run", "--rm", "-i",
        "--device", "/dev/snd",
        "-e", "PULSE_RUNTIME_PATH=/run/user/1000/pulse",
        "-v", "/run/user/1000/pulse:/run/user/1000/pulse",
        "ghcr.io/mbailey/voice-mcp:latest"
      ],
      "env": {
        "OPENAI_API_KEY": "your-openai-key"
      }
    }
  }
}

{
  "mcpServers": {
    "voice-mcp": {
      "command": "voice-mcp",
      "env": {
        "OPENAI_API_KEY": "your-openai-key"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.
Z
Zen MCP Server
Zen MCP is a multi-model AI collaborative development server that provides enhanced workflow tools and cross-model context management for AI coding assistants such as Claude and Gemini CLI. It supports seamless collaboration of multiple AI models to complete development tasks such as code review, debugging, and refactoring, and can maintain the continuation of conversation context between different workflows.
Python
18
5 points
O
Opendia
OpenDia is an open - source browser extension tool that allows AI models to directly control the user's browser, perform automated operations using existing login status, bookmarks and other data, support multiple browsers and AI models, and focus on privacy protection.
JavaScript
15
5 points
N
Notte Browser
Certified
Notte is an open-source full-stack network AI agent framework that provides browser sessions, automated LLM-driven agents, web page observation and operation, credential management, etc. It aims to transform the Internet into an agent-friendly environment and reduce the cognitive burden of LLMs by describing website structures in natural language.
701
4.5 points
B
Bing Search MCP
An MCP server for integrating Microsoft Bing Search API, supporting web page, news, and image search functions, providing network search capabilities for AI assistants.
Python
262
4 points
C
Cloudflare
Changesets is a build tool for managing versions and releases in multi - package or single - package repositories.
TypeScript
1.5K
5 points
E
Eino
Eino is an LLM application development framework designed specifically for Golang, aiming to simplify the AI application development process through concise, scalable, reliable, and efficient component abstraction and orchestration capabilities. It provides a rich component library, powerful graphical orchestration functions, complete stream processing support, and a highly scalable aspect mechanism, covering the full-cycle toolchain from development to deployment.
Go
3.5K
5 points
M
Modelcontextprotocol
Certified
This project is an implementation of an MCP server integrated with the Sonar API, providing real-time web search capabilities for Claude. It includes guides on system architecture, tool configuration, Docker deployment, and multi-platform integration.
TypeScript
1.2K
5 points
S
Serena
Serena is a powerful open - source coding agent toolkit that can transform LLMs into full - fledged agents that can work directly on codebases. It provides IDE - like semantic code retrieval and editing tools, supports multiple programming languages, and can be integrated with multiple LLMs via the MCP protocol or the Agno framework.
Python
938
5 points
Featured MCP Services
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.8K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
154
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
201
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
892
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.7K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
616
5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
797
4.8 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
335
4.5 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2025AIbase